@seoagent-official/seoagent 1.59.0 → 1.61.0

package/README.md

@@ -161,7 +161,7 @@ Same agent-native convenience. None of the lock-in.
 
 **Open Knowledge Format bundle (AEO/GEO)** — Generate a Google [Open Knowledge Format](https://github.com/GoogleCloudPlatform/knowledge-catalog/tree/main/okf) bundle for your site — a curated, agent-readable knowledge layer so ChatGPT, Claude, Perplexity, and Google's AI understand and cite your business accurately. Claude maps your `.seoagent/` knowledge into OKF markdown; `seoagent okf scaffold` and `seoagent okf validate` handle the structure. Saved to `.seoagent/okf/`.
 
-**AI Citation Scorecard (the measurement half of AEO)** — Publishing an OKF bundle makes you *citable*; `seoagent citations` tells you whether it's *working*. It runs a set of buyer-intent questions through the Claude Agent SDK **with live web search** and reports which ones surface your business — a web-grounded proxy for how ChatGPT, Perplexity, and Google's AI Overviews answer. Saved to `.seoagent/citations/scorecard.md`. (Honest by design: it measures Claude + web search, not a per-engine guarantee — re-run over time to watch the trend.)
+**AI Citation Tracker (the measurement half of AEO)** — Publishing an OKF bundle makes you *citable*; `seoagent citations` tells you whether it's *working*. It runs a set of buyer-intent questions through the Claude Agent SDK **with live web search** and reports which ones surface your business — a web-grounded proxy for how ChatGPT, Perplexity, and Google's AI Overviews answer. It's a real tracker, not a one-shot read: every run is saved to `.seoagent/citations/history/` and the scorecard shows the **trend** vs your last run, the **URL each engine cited** (yours when you win, the page that beat you when you don't), and — with `--competitors "Frase,Otterly"` — a **share-of-voice** table ranking you against them. Saved to `.seoagent/citations/scorecard.md`. The paid trackers (Frase, Otterly, Profound) gate exactly this behind $50–500/mo; we do it free on your own model. (Honest by design: it measures Claude + web search, not a per-engine guarantee.)
 
 **Compounding Roadmap** — Prioritized action plan that updates after every action. Saved to `.seoagent/roadmap.md`. Persistent changelog at `.seoagent/changelog.md`.
 
@@ -300,7 +300,7 @@ Grouped by what they're for. Run as bare `seoagent <cmd>` after the one-time `np
 | `keywords` | Enrich your existing keyword inventory with real search volume + difficulty. `--discover` finds new targets; `--competitors` shows the gap (paid). |
 | `internal-links` | Generate internal-linking recommendations from your existing pages + topic clusters. |
 | `okf [scaffold\|validate]` | Generate an [Open Knowledge Format](https://github.com/GoogleCloudPlatform/knowledge-catalog/tree/main/okf) bundle for AI agents (AEO/GEO) → `.seoagent/okf/`. `scaffold` starts it; `validate` checks `type` fields, ISO-8601 timestamps + cross-links. The skill fills the content. |
-| `citations` | Measure whether answer engines cite you (AEO/GEO). Runs buyer-intent queries through the Claude Agent SDK **with live web search** → `.seoagent/citations/scorecard.md`. `--queries <1-12>` (default 6), `--model <name>`, `--json`. Uses your `claude login` session or `ANTHROPIC_API_KEY`, same as `process`. |
+| `citations` | Track whether answer engines cite you (AEO/GEO). Runs buyer-intent queries through the Claude Agent SDK **with live web search** → `.seoagent/citations/scorecard.md`, with run **history** (`.seoagent/citations/history/`), trend vs last run, source-attribution, and competitor **share-of-voice**. `--queries <1-12>` (default 6), `--competitors <a,b,c>`, `--model <name>`, `--json`. Uses your `claude login` session or `ANTHROPIC_API_KEY`, same as `process`. |
 | `generate-image` | Generate hero / inline images via the detected provider (BYO API key). |
 
 **Account + maintenance**